Combined classification method for prosodic stress recognition in Farsi language

Gharavian, Davood; Sheikhan, Mansour; Ghasemi, Sh. S.

doi:10.1007/s10772-018-9508-7

Cited by 4 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In terms of the related work in the field of automatic lexical stress detection and mapping for low-resource languages, Ni, Liu, and Xu [20] developed a hierarchical modelbased boosting classification and regression tree (CART) for Mandarin stress detection using acoustic evidence and textual information. Gharavian, Sheikhan, and Ghasemi [21] developed a combined classification model for lexical stress detection in Farsi (HMM was used to segment stressed sentences, additional features were extracted from pitch and formant frequencies, and six feature sets were selected using fast correlation-based filter feature selection). For Hindi, a hybrid model (rule-based and statistical learning) was used [22].…”

Section: Related Workmentioning

confidence: 99%

System for Automatic Assignment of Lexical Stress in Croatian

Preradović

Prskalo

2022

Electronics

View full text Add to dashboard Cite

It is very popular today to integrate voice interfaces into IoT devices. The pronunciation and proper prosody of speech play a major role in the intelligibility and naturalness of synthesized voices. Each language has its own prosodic characteristics. In this paper, we present the results of a study aimed at testing the applicability of methods for modelling and predicting the prosodic features of the Croatian language. The extent to which their performance can be improved by incorporating linguistic features and linguistic peculiarities specific to the Croatian language was investigated. In the model learning process, tree classification was used to predict the lexical stress position and the type of stress in a word, and a lexicon of 1,011,785 word forms was used as the model learning set. Separate models were created for predicting the position and type of lexical stress. The results improved significantly after the rules for atonic words (clitics) were applied. A hybrid approach combining a rule-based approach and a modelling approach was also proposed. The final accuracy of assigning lexical stress using the hybrid approach was 95.3%.

show abstract

Section: Related Workmentioning

confidence: 99%

System for Automatic Assignment of Lexical Stress in Croatian

Preradović

Prskalo

2022

Electronics

View full text Add to dashboard Cite

show abstract

“…Since this technique is directly geared towards maximizing the fisher score, while the mean and variance of each class can be easily calculated, it has the potential to be applied to multi-class data. Various feature quality test metrics, such as Information Gain [28]- [30], Gain ratio [31], Gini Decrease [32], Anova [33], [34], Chi-Square [35], ReliefF [36], [37], and Fast Correlation-Based Feature selection (FCBF) [38], [39], are used to test the feature quality of the proposed Box-Cox transformation and Quadratic transformation, before finally comparing their respective performance.…”

Section: Introductionmentioning

confidence: 99%

Separability-based Quadratic Feature Transformation to Improve Classification Performance

Sudibyo,

Rustad,

Andono

et al. 2023

IJACSA

View full text Add to dashboard Cite

Feature transformation is an essential part of data preprocessing to improve the predictive performance of machine learning (ML) algorithms. Box-Cox transformation with the goal of separability is proven to align with the performance improvement of ML algorithms. However, the features mapped using Box-Cox transformation preserve the order of the data, so it is ineffective when used to improve the separability of multimodal distributed features. This research aims to build a feature transformation method using quadratic functions to improve class separability that can adaptively change the order of the data when necessary. Fisher score (Fs) measures the separability level by maximizing the Fisher's Criteria of the quadratic function. In addition to increasing the Fs value of each feature, this method can also make the feature more informative, as evidenced by the increasing value of information gain, information gain ratio, Gini decrease, ANOVA, Chi-Square, reliefF, and FCBF. The increase in Fs is particularly significant for bimodally distributed features. Experiments were conducted on 11 public datasets with two statistical-based machine learning algorithms representing linear and nonlinear ML algorithms to validate the success of this method, namely LDA and QDA. The experimental results show an improvement in accuracy in almost all datasets and ML algorithms, where the highest accuracy improvement is 0.268 for LDA and 0.188 for QDA.

show abstract

“…Speech recognition in machine learning has become quite an exciting field of study. Typically, we would extract acoustic features from the speech data to determine the information's modality (of semiotics manner) and then feed it to the machine learning algorithms for the specific recognition task (6). Unfortunately, machine learning is a data-driven model.…”

Section: Introductionmentioning

confidence: 99%

Exploring the Time-efficient Evolutionary-based Feature Selection Algorithms for Speech Data under Stressful Work Condition

Adi

Junaedi

Frismanda

et al. 2021

emitter

View full text Add to dashboard Cite

Initially, the goal of Machine Learning (ML) advancements is faster computation time and lower computation resources, while the curse of dimensionality burdens both computation time and resource. This paper describes the benefits of the Feature Selection Algorithms (FSA) for speech data under workload stress. FSA contributes to reducing both data dimension and computation time and simultaneously retains the speech information. We chose to use the robust Evolutionary Algorithm, Harmony Search, Principal Component Analysis, Genetic Algorithm, Particle Swarm Optimization, Ant Colony Optimization, and Bee Colony Optimization, which are then to be evaluated using the hierarchical machine learning models. These FSAs are explored with the conversational workload stress data of a Customer Service hotline, which has daily complaints that trigger stress in speaking. Furthermore, we employed precisely 223 acoustic-based features. Using Random Forest, our evaluation result showed computation time had improved 3.6 faster than the original 223 features employed. Evaluation using Support Vector Machine beat the record with 0.001 seconds of computation time.

show abstract

Combined classification method for prosodic stress recognition in Farsi language

Cited by 4 publications

References 37 publications

System for Automatic Assignment of Lexical Stress in Croatian

System for Automatic Assignment of Lexical Stress in Croatian

Separability-based Quadratic Feature Transformation to Improve Classification Performance

Exploring the Time-efficient Evolutionary-based Feature Selection Algorithms for Speech Data under Stressful Work Condition

Contact Info

Product

Resources

About